The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences

TL;DR

This paper introduces a comprehensive dataset with multiple distortion types for visual JND modeling, enabling more generalized human visual system understanding beyond compression artifacts.

Contribution

It creates the first large-scale JND dataset covering 25 distortion types, using a coarse-to-fine selection process with crowdsourced subjective assessments.

Findings

Dataset contains 106 source images and 1,642 JND maps.

Covers 25 different distortion types.

Enables generalized JND modeling beyond compression distortions.

Abstract

Recently, with the development of deep learning, a number of Just Noticeable Difference (JND) datasets have been built for JND modeling. However, all the existing JND datasets only label the JND points based on the level of compression distortion. Hence, JND models learned from such datasets can only be used for image/video compression. As known, JND is a major characteristic of the human visual system (HVS), which reflects the maximum visual distortion that the HVS can tolerate. Hence, a generalized JND modeling should take more kinds of distortion types into account. To benefit JND modeling, this work establishes a generalized JND dataset with a coarse-to-fine JND selection, which contains 106 source images and 1,642 JND maps, covering 25 distortion types. To this end, we proposed a coarse JND candidate selection scheme to select the distorted images from the existing Image Quality Assessment (IQA) datasets as JND candidates instead of generating JND maps ourselves. Then, a fine JND selection is carried out on the JND candidates with a crowdsourced subjective assessment.